首页
登录
注册
基于伪Wigner-Ville分布和Rényi熵的显著图目标检测
Target detection of saliency map based on pseudo Wigner-Ville distribution and Rényi entropy
-
摘要: 在复杂背景中,往往难以实现目标的自动检测,依据Wigner-Ville分布能够对图像在空间域/空间频率域上联合表示的特性.研究了图像经伪Wigner-Ville分布后Rényi熵的统计特性,分析了人造目标的出现会引起自然场景中Rényi熵统计特性的变化,并在此基础上提出了一种新的基于伪Wigner-Ville分布和Renyi熵的显著图生成方法.之后对显著图进行简便的阈值分割,完成目标检测.实验结果表明,所提出的方法能够有效地检测复杂地面背景中的军用车辆.
-
关键词:
- 伪Wigner-Ville分布 /
- Rényi熵 /
- 显著图 /
- 目标检测
Abstract: Automatic target detection is always difficult in complex background. The Wigner-Ville distribution has a good characteristic that the images can be represented in spatial/spatial-frequency domains. Through the pseudo Wigner-Ville distribution, the statistical property of Rényi entropy is studied. The change of Rényi entropy' s statistical property in natural images when the man-made objects appear is analysed. Then a novel method for generating saliency map based on pseudo Wigner-Ville distribution and Renyi entropy is proposed. Target detection is performed when the saliency map is segmented using a simple and convenient threshold method. Experimental results show the proposed method can detect the military vehicles from complex earth background effectively. -
-
计量
- 文章访问数: 474
- HTML全文浏览数: 14
- PDF下载数: 0
- 施引文献: 0
下载: